dlin-cli 0.1.2a1__tar.gz → 0.2.0a2__tar.gz

{dlin_cli-0.1.2a1 → dlin_cli-0.2.0a2}/Cargo.lock

@@ -231,7 +231,23 @@ checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
 
 [[package]]
 name = "dlin"
-version = "0.1.2-alpha.1"
+version = "0.2.0-alpha.2"
+dependencies = [
+ "anyhow",
+ "clap",
+ "dlin-core",
+ "libc",
+ "path-slash",
+ "polyglot-sql",
+ "regex",
+ "serde-saphyr",
+ "serde_json",
+ "tempfile",
+]
+
+[[package]]
+name = "dlin-core"
+version = "0.2.0-alpha.2"
 dependencies = [
  "anyhow",
  "clap",
@@ -239,10 +255,10 @@ dependencies = [
  "globset",
  "indexmap",
  "insta",
- "libc",
  "minijinja",
  "path-slash",
  "petgraph",
+ "polyglot-sql",
  "rayon",
  "regex",
  "serde",
@@ -250,7 +266,7 @@ dependencies = [
  "serde_json",
  "serial_test",
  "tempfile",
- "thiserror",
+ "thiserror 2.0.18",
  "walkdir",
 ]
 
@@ -599,6 +615,18 @@ version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
 
+[[package]]
+name = "polyglot-sql"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b155f49ed6a6bb331a4aead9dc2f5f69a70f2130edd2614a0387a82ac1eee5e6"
+dependencies = [
+ "serde",
+ "serde_json",
+ "thiserror 1.0.69",
+ "unicode-segmentation",
+]
+
 [[package]]
 name = "prettyplease"
 version = "0.2.37"
@@ -733,7 +761,7 @@ checksum = "d55ae5ea09894b6d5382621db78f586df37ef18ab581bf32c754e75076b124b1"
 dependencies = [
  "arraydeque",
  "smallvec",
- "thiserror",
+ "thiserror 2.0.18",
 ]
 
 [[package]]
@@ -900,13 +928,33 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "thiserror"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
+dependencies = [
+ "thiserror-impl 1.0.69",
+]
+
 [[package]]
 name = "thiserror"
 version = "2.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
 dependencies = [
- "thiserror-impl",
+ "thiserror-impl 2.0.18",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
 ]
 
 [[package]]
@@ -926,6 +974,12 @@ version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
 
+[[package]]
+name = "unicode-segmentation"
+version = "1.13.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9629274872b2bfaf8d66f5f15725007f635594914870f65218920345aa11aa8c"
+
 [[package]]
 name = "unicode-width"
 version = "0.2.2"

{dlin_cli-0.1.2a1 → dlin_cli-0.2.0a2}/Cargo.toml

@@ -1,21 +1,15 @@
-[package]
-name = "dlin"
-version = "0.1.2-alpha.1"
+[workspace]
+members = ["crates/*"]
+resolver = "3"
+
+[workspace.package]
+version = "0.2.0-alpha.2"
 edition = "2024"
-description = "A fast CLI tool for dbt model lineage analysis"
 license = "MIT"
 repository = "https://github.com/eitsupi/dlin"
 homepage = "https://github.com/eitsupi/dlin"
-readme = "README.md"
-keywords = ["dbt", "lineage", "dag", "sql", "cli"]
-categories = ["command-line-utilities", "visualization"]
-
-[[bin]]
-name = "dlin"
-path = "src/main.rs"
 
-[dependencies]
-clap = { version = "4", features = ["derive", "env"] }
+[workspace.dependencies]
 petgraph = "0.6"
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
@@ -29,24 +23,30 @@ indexmap = "2"
 minijinja = "2"
 rayon = "1"
 globset = "0.4"
+polyglot-sql = { version = "0.4.0", default-features = false, features = ["all-dialects", "semantic"] }
 path-slash = "0.2.1"
-
-[target.'cfg(unix)'.dependencies]
+clap = { version = "4", features = ["derive", "env"] }
 libc = "0.2"
 
-[lints.rust]
+# dev
+tempfile = "3"
+insta = "1"
+serial_test = "3.4.0"
+
+# internal
+dlin-core = { version = "0.2.0-alpha.2", path = "crates/dlin-core" }
+
+[workspace.lints.rust]
 unexpected_cfgs = { level = "warn", check-cfg = ['cfg(tarpaulin_include)'] }
 
 [profile.dist]
 inherits = "release"
-lto = "fat"
+# FIXME: fat LTO causes polyglot-sql's large match statements to be inlined into
+# the dlin binary, bloating it from ~7.5 MB to ~12 MB. Use thin LTO until the
+# upstream semantic→generate feature dependency is removed from polyglot-sql,
+# after which generator.rs will be excluded from the build entirely.
+lto = "thin"
 codegen-units = 1
 strip = true
 opt-level = "s"
 panic = "abort"
-
-[dev-dependencies]
-tempfile = "3"
-regex = "1"
-insta = "1"
-serial_test = "3.4.0"

{dlin_cli-0.1.2a1 → dlin_cli-0.2.0a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dlin-cli
-Version: 0.1.2a1
+Version: 0.2.0a2
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers

dlin_cli-0.2.0a2/crates/dlin/Cargo.toml

@@ -0,0 +1,36 @@
+[package]
+name = "dlin"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+repository.workspace = true
+homepage.workspace = true
+description = "A fast CLI tool for dbt model lineage analysis"
+readme = "README.md"
+keywords = ["dbt", "lineage", "dag", "sql", "cli"]
+categories = ["command-line-utilities", "visualization"]
+
+[[bin]]
+name = "dlin"
+path = "src/main.rs"
+
+[dependencies]
+dlin-core = { workspace = true, features = ["clap", "column-lineage"] }
+clap = { workspace = true }
+anyhow = { workspace = true }
+serde_json = { workspace = true }
+path-slash = { workspace = true }
+polyglot-sql = { workspace = true }
+
+[target.'cfg(unix)'.dependencies]
+libc = { workspace = true }
+
+[dev-dependencies]
+dlin-core = { workspace = true }
+tempfile = { workspace = true }
+regex = { workspace = true }
+serde_json = { workspace = true }
+serde-saphyr = { workspace = true }
+
+[lints]
+workspace = true

dlin_cli-0.2.0a2/crates/dlin/README.md

@@ -0,0 +1,292 @@
+# dlin
+
+[![Crates.io](https://img.shields.io/crates/v/dlin)](https://crates.io/crates/dlin)
+[![PyPI](https://img.shields.io/pypi/v/dlin-cli)](https://pypi.org/project/dlin-cli/)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/eitsupi/dlin)
+
+dbt lineage analysis CLI that parses SQL files directly. No `dbt compile`, no Python, no `manifest.json`.
+
+Builds a dependency graph from `ref()` and `source()` calls in SQL. Designed for AI agents and CI pipelines.
+
+## Motivation
+
+When I edited dbt models in VS Code, [dbt Power User](https://marketplace.visualstudio.com/items?itemName=innoverio.vscode-dbt-power-user) was my go-to companion for navigating lineage. AI agents have no such companion. I watched them `grep` through dbt projects to find model dependencies. It works, but they end up calling `grep` repeatedly and relying on fragile string matching to piece together `ref()` and `source()` relationships.
+
+dlin is designed to fill that gap: a CLI tool that lets AI agents understand a dbt project's structure without falling back to `grep`. It is equally useful for humans, and its stdin/stdout interface makes it easy to combine with `jq`, `git diff`, and other CLI tools.
+
+To replace `grep`, speed and size matter. dlin is a small, self-contained binary with no runtime dependencies. It parses SQL directly, evaluates common Jinja patterns without Python, parallelizes file I/O, and caches aggressively.
+
+The key idea behind dlin is that finding the right models fast is what matters most. AI agents can read SQL and trace column-level relationships on their own; the hard part is knowing which models to look at in the first place. So dlin focuses on model-level lineage and makes that as fast as possible.
+
+## Install
+
+### Cargo (Rust)
+
+```sh
+cargo install dlin
+```
+
+### pip / uv (Python)
+
+For convenience, dlin is also available as a Python package. The installed binary is native and does not require Python at runtime.
+
+```sh
+pip install dlin-cli   # or: uv tool install dlin-cli
+```
+
+### GitHub Releases
+
+Pre-built binaries for Linux, macOS, and Windows are available on the [Releases](https://github.com/eitsupi/dlin/releases) page. You can also use the installer scripts:
+
+macOS / Linux:
+
+```sh
+curl --proto '=https' --tlsv1.2 -LsSf https://github.com/eitsupi/dlin/releases/latest/download/dlin-installer.sh | sh
+```
+
+Windows (PowerShell):
+
+```powershell
+powershell -ExecutionPolicy Bypass -c "irm https://github.com/eitsupi/dlin/releases/latest/download/dlin-installer.ps1 | iex"
+```
+
+## Quick start
+
+```sh
+# Full lineage graph
+dlin graph -p path/to/dbt/project
+
+# Downstream impact analysis
+dlin impact orders
+
+# List models as JSON
+dlin list -o json --json-fields unique_id,file_path
+
+# Pipe changed files into lineage
+git diff --name-only main | dlin graph -o json
+```
+
+## AI agent integration
+
+No MCP server or tool configuration needed.
+Just install dlin and add the following to your `AGENTS.md`, `CLAUDE.md`, or system prompt:
+
+````md
+## dbt project structure analysis
+
+Use `dlin` to explore dbt model dependencies.
+Do NOT grep/cat/find through SQL files.
+
+```bash
+dlin summary                                           # Project overview (start here)
+dlin graph <model> -u 2 -d 1 -q                        # Upstream/downstream lineage
+dlin impact <model>                                    # Downstream impact with severity
+dlin list -o json --json-fields unique_id,sql_content  # Read SQL content
+git diff --name-only main | dlin graph -q              # Lineage of changed files
+```
+
+For full option reference: `dlin --help`, `dlin graph --help`, etc.
+````
+
+The key line is **"Do NOT grep/cat/find through SQL files"** — without it, agents default to familiar tools. `dlin --help` is designed for tool discovery, so the prompt can stay minimal.
+
+## Features
+
+- **No dependencies**: single binary, no Python, no `manifest.json`
+- **Recursive upstream / downstream**: `-u N` / `-d N` to control traversal depth
+- **Impact analysis with severity**: `dlin impact` scores downstream nodes and flags exposure reachability
+- **Composable**: stdin accepts model names or file paths; pipe with `jq`, `dlin list`, `git diff`, etc.
+- **Agent-friendly**: `--error-format json` emits structured `{"level","what","why","hint"}` on stderr; `--help` is designed for tool discovery
+
+## Mermaid diagrams
+
+dlin outputs Mermaid flowcharts that render natively on GitHub, GitLab, Notion, and other Markdown environments.
+
+### Simplified graphs with `--collapse`
+
+Automatically remove intermediate nodes to see just the endpoints (nodes with no predecessors or no successors); everything in between becomes transitive "(via N)" edges:
+
+```sh
+# Collapse intermediate models — only endpoints remain
+dlin graph --collapse -o mermaid
+
+# Focal mode: keep only sources, exposures, and specified focus models
+# (ignores BFS window pseudo-endpoints — ideal with -u/-d limits)
+dlin graph orders --collapse=focal -u 3 -o mermaid
+```
+
+```mermaid
+flowchart LR
+    exposure_weekly_report>"weekly_report"]
+    model_combined_orders["combined_orders"]
+    model_order_summary["order_summary"]
+    source_raw_customers(["raw.customers"])
+    source_raw_orders(["raw.orders"])
+    source_raw_payments(["raw.payments"])
+
+    source_raw_customers ==>|"exposure (via 2)"| exposure_weekly_report
+    source_raw_orders ==>|"exposure (via 3)"| exposure_weekly_report
+    source_raw_orders -.->|"source (via 1)"| model_combined_orders
+    source_raw_orders -.->|"source (via 1)"| model_order_summary
+    source_raw_payments ==>|"exposure (via 3)"| exposure_weekly_report
+    source_raw_payments -.->|"source (via 1)"| model_order_summary
+
+    classDef model fill:#4A90D9,stroke:#333,color:#fff
+    classDef source fill:#27AE60,stroke:#333,color:#fff
+    classDef exposure fill:#E74C3C,stroke:#333,color:#fff
+    class exposure_weekly_report exposure
+    class model_combined_orders model
+    class model_order_summary model
+    class source_raw_customers source
+    class source_raw_orders source
+    class source_raw_payments source
+```
+
+Positional focus models are always preserved during collapse, so `dlin graph orders --collapse` keeps `orders` even if it would otherwise be intermediate.
+
+### Pipe to build focused diagrams
+
+Combine `dlin list`, `jq`, and `dlin graph` to extract exactly the nodes you want:
+
+```sh
+# Staging models → 1 hop downstream, models only, grouped by directory
+dlin list -s 'path:models/staging' -o json | jq -r '.[].label' |
+  dlin graph -d 1 --node-type model --group-by directory -o mermaid
+```
+
+```mermaid
+flowchart LR
+    subgraph models_marts["models/marts"]
+        model_combined_orders["combined_orders"]
+        model_customers["customers"]
+        model_order_summary["order_summary"]
+        model_orders["orders"]
+    end
+    subgraph models_staging["models/staging"]
+        model_stg_customers["stg_customers"]
+        model_stg_online_orders["stg_online_orders"]
+        model_stg_orders["stg_orders"]
+        model_stg_payments["stg_payments"]
+        model_stg_retail_orders["stg_retail_orders"]
+    end
+
+    model_orders -->|ref| model_customers
+    model_stg_customers -->|ref| model_customers
+    model_stg_online_orders -->|ref| model_combined_orders
+    model_stg_orders -->|ref| model_order_summary
+    model_stg_orders -->|ref| model_orders
+    model_stg_payments -->|ref| model_order_summary
+    model_stg_payments -->|ref| model_orders
+    model_stg_retail_orders -->|ref| model_combined_orders
+
+    classDef model fill:#4A90D9,stroke:#333,color:#fff
+    class model_combined_orders model
+    class model_customers model
+    class model_order_summary model
+    class model_orders model
+    class model_stg_customers model
+    class model_stg_online_orders model
+    class model_stg_orders model
+    class model_stg_payments model
+    class model_stg_retail_orders model
+```
+
+### Column names in nodes with `--show-columns`
+
+Add `--show-columns` to include column names inside Mermaid node labels — useful for understanding what each model produces at a glance:
+
+```sh
+dlin graph orders -u 1 -d 0 --show-columns --node-type model,source -o mermaid
+```
+
+```mermaid
+flowchart LR
+    model_orders["orders<br/>---<br/>order_id, customer_id, order_date, status, total_amount, payment_method"]
+    model_stg_orders["stg_orders<br/>---<br/>order_id, customer_id, order_date, status"]
+    model_stg_payments["stg_payments<br/>---<br/>payment_id, order_id, amount, payment_method"]
+
+    model_stg_orders -->|ref| model_orders
+    model_stg_payments -->|ref| model_orders
+
+    classDef model fill:#4A90D9,stroke:#333,color:#fff
+    class model_orders model
+    class model_stg_orders model
+    class model_stg_payments model
+```
+
+Combines well with `--collapse` to show rich detail on fewer endpoint nodes.
+
+### Other graph options
+
+```sh
+dlin graph orders -u 2 -d 1                            # focus on specific model
+dlin graph -o mermaid --collapse --show-columns        # columns in collapsed nodes
+dlin graph orders --collapse=focal -u 3 -o mermaid    # focal: sources + exposures + orders
+dlin graph -o mermaid --group-by directory             # group by directory
+dlin graph -o mermaid --direction tb                   # top-to-bottom layout
+dlin graph --node-type source,exposure                 # filter by node type
+dlin graph -o dot | dot -Tsvg > out.svg                # Graphviz rendering
+```
+
+Output formats: ASCII (default), JSON, Mermaid, Graphviz DOT, Plain, SVG, HTML.
+
+## Key subcommands
+
+### `list`
+
+```sh
+dlin list                                                   # all models and sources
+dlin list orders -o json --json-fields unique_id,file_path  # specific model as JSON
+dlin list --node-type source                                # sources only
+```
+
+### `impact`
+
+```sh
+$ dlin impact orders
+Impact Analysis: orders
+==================================================
+Overall Severity: CRITICAL
+
+Summary:
+  Affected models:    1
+  Affected tests:     1
+  Affected exposures: 1
+
+Impacted Nodes:
+  [critical] weekly_report (exposure, distance: 1)
+  [high    ] customers (model, distance: 1) [models/marts/customers.sql]
+  [low     ] assert_orders_positive_amount (test, distance: 1)
+```
+
+## Filtering
+
+```sh
+dlin graph -s tag:finance,path:marts  # selector expressions (union)
+dlin graph --node-type model,source   # filter by node type
+```
+
+## Data sources
+
+dlin aims to work without `dbt compile`. By default it parses SQL files directly, but it can also leverage a pre-compiled `manifest.json` for additional accuracy when one is available.
+
+**SQL parsing (default)**: extracts `ref()` and `source()` from SQL via regex + Jinja template evaluation. No Python or dbt needed. Generic tests (`not_null`, `unique`, `relationships`, etc.) are inferred from YAML schema declarations.
+
+**Manifest mode** (`--source manifest`): reads a pre-compiled `manifest.json` for full accuracy with complex Jinja logic.
+
+### Limitations of SQL parse mode
+
+- `var()` resolves from `dbt_project.yml` only (`--vars` CLI overrides not supported)
+- Runtime context (`target.type`, `env_var()`) is not evaluated
+- Conditional Jinja branches use default values; non-default paths may be missed
+- Generic test IDs are dlin-specific (e.g. `test.not_null.orders.order_id`) and do not match dbt's naming; use manifest mode when exact test IDs matter
+
+When these limitations matter, use `--source manifest`.
+
+## Credits
+
+Hard fork of [dbt-lineage-viewer](https://github.com/sipemu/dbt-lineage-viewer) by Simon Muller (MIT license). The original focused on TUI-based exploration; dlin removes the TUI and targets non-interactive use: scripting, CI, and AI agents.
+
+## License
+
+MIT